A Novel Non-Orthogonal Joint Diagonalization Cost Function for ICA

Simple item page
dc.contributor.advisorKrishnaprasad, Perinkulam S.en_US
dc.contributor.authorAfsari, Bijanen_US
dc.contributor.authorKrishnaprasad, Perinkulam S.en_US
dc.contributor.departmentISRen_US
dc.date.accessioned2007-05-23T10:18:13Z
dc.date.available2007-05-23T10:18:13Z
dc.date.issued2005en_US
dc.description.abstractWe present a new scale-invariant cost function for non-orthogonal joint-diagonalization of a set of symmetric matrices with application to Independent Component Analysis (ICA). We derive two gradient minimization schemes to minimize this cost function. We also consider their performance in the context of an ICA algorithm based on non-orthogonal joint diagonalization.en_US
dc.format.extent127401 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/6571
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 2005-106en_US
dc.subjectOptimization on Manifoldsen_US
dc.subjectBlind Source Separationen_US
dc.titleA Novel Non-Orthogonal Joint Diagonalization Cost Function for ICAen_US
dc.typeTechnical Reporten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
TR_2005-106.pdf
Size:
124.42 KB
Format:
Adobe Portable Document Format
Download

Collections

Institute for Systems Research Technical Reports